
# Importing libraries for data analysis and visualization

# NumPy: Library for numerical computations and array manipulation
import numpy as np

# Pandas: Data manipulation and analysis library
import pandas as pd

# Seaborn: Data visualization library built on Matplotlib
import seaborn as sns

# Matplotlib.pyplot: Submodule of Matplotlib for creating plots
import matplotlib.pyplot as plt

# Plotly.graph_objs: Part of the Plotly library for interactive plots
import plotly.graph_objs as go

# Plotly.express: High-level interface for interactive visualizations using Plotly
import plotly.express as px

# os: Module for interacting with the operating system
import os

# WordCloud: Library for creating word clouds from text data
from wordcloud import WordCloud

# plotly.subplots.make_subplots: Function for creating subplots within a single Plotly figure
from plotly.subplots import make_subplots

# Jupyter Notebook magic command for displaying Matplotlib plots inline
%matplotlib inline


# Read data from the CSV file into the 'aib' DataFrame
aib = pd.read_csv("Airbnb_Open_Data.csv")

# Create a new DataFrame 'aib1' with a column 'house_rules' from 'aib'
aib1 = pd.DataFrame()
aib1["house_rules"] = aib["house_rules"]

/var/folders/sh/dbwfh3gx18n7xjl99467b4_m0000gn/T/ipykernel_3275/311372415.py:2: DtypeWarning:

Columns (25) have mixed types. Specify dtype option on import or set low_memory=False.


#To display the first 10 rows of the aib DataFrame
aib.head(10)


#Total data in the dataset.
len(aib)

102599


#count the nan values
nan_counts = aib.isna().sum()
nan_counts

id                                     0
NAME                                 250
host id                                0
host_identity_verified               289
host name                            406
neighbourhood group                   29
neighbourhood                         16
lat                                    8
long                                   8
country                              532
country code                         131
instant_bookable                     105
cancellation_policy                   76
room type                              0
Construction year                    214
price                                247
service fee                          273
minimum nights                       409
number of reviews                    183
last review                        15893
reviews per month                  15879
review rate number                   326
calculated host listings count       319
availability 365                     448
house_rules                        52131
license                           102597
dtype: int64


#Dropping the useless columns
columns_to_drop = ['license', 'country', 'country code','last review', 'host id','house_rules', 'reviews per month']
aib.drop(columns=columns_to_drop, axis=1, inplace=True)


#We neeed to delete nan values from the dataset.
aib = aib.dropna()


#Checking data types of the data.
aib.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 99502 entries, 0 to 102598
Data columns (total 19 columns):
 #   Column                          Non-Null Count  Dtype  
---  ------                          --------------  -----  
 0   id                              99502 non-null  int64  
 1   NAME                            99502 non-null  object 
 2   host_identity_verified          99502 non-null  object 
 3   host name                       99502 non-null  object 
 4   neighbourhood group             99502 non-null  object 
 5   neighbourhood                   99502 non-null  object 
 6   lat                             99502 non-null  float64
 7   long                            99502 non-null  float64
 8   instant_bookable                99502 non-null  object 
 9   cancellation_policy             99502 non-null  object 
 10  room type                       99502 non-null  object 
 11  Construction year               99502 non-null  float64
 12  price                           99502 non-null  object 
 13  service fee                     99502 non-null  object 
 14  minimum nights                  99502 non-null  float64
 15  number of reviews               99502 non-null  float64
 16  review rate number              99502 non-null  float64
 17  calculated host listings count  99502 non-null  float64
 18  availability 365                99502 non-null  float64
dtypes: float64(8), int64(1), object(10)
memory usage: 15.2+ MB


# Convert the 'Construction year' column to string
aib['Construction year'] = aib['Construction year'].astype(str)

# Extract the numeric part and convert it to integers
aib['Construction year'] = aib['Construction year'].str.extract(r'(\d+)').astype(int)


#Changing the all values in the neighbourhood group column to the lower case.
aib['neighbourhood group'] = aib['neighbourhood group'].str.lower()


#changing the spelling mistakes
aib['neighbourhood group'] = aib['neighbourhood group'].str.replace('brooklyn', 'brookln')


# find and replace the dollar sign with empty string
aib['price'] = aib['price'].str.replace(r'\$', '', regex=True) 
#replace the commas sign with empty string
aib['price'] = aib['price'].str.replace(r',', '', regex=True)  
#changing the data type, object to int
aib['price'] = pd.to_numeric(aib['price'])


#Replacing the dollor sign, commas and spaces from the service fee column.
aib['service fee'] = aib['service fee'].str.replace(r'\$', '', regex=True)  
aib['service fee'] = aib['service fee'].str.replace(r',', '', regex=True)  
aib['service fee'] = pd.to_numeric(aib['service fee'])


#we are replacing values in availability 365, from <0 to 0.
negative_values_count = aib[aib['availability 365'] < 0]['availability 365'].value_counts().sum()
aib = aib[aib['availability 365'] <= 365]


# Convert 'minimum nights' column to integer data type
aib['minimum nights'] = aib['minimum nights'].astype(int)

# Convert 'number of reviews' column to integer data type
aib['number of reviews'] = aib['number of reviews'].astype(int)

# Convert 'review rate number' column to integer data type
aib['review rate number'] = aib['review rate number'].astype(int)

# Convert 'availability 365' column to integer data type
aib['availability 365'] = aib['availability 365'].astype(int)

# Convert 'calculated host listings count' column to integer data type
aib['calculated host listings count'] = aib['calculated host listings count'].astype(int)


# Count the number of listings ('id') in each 'room type' category
# Sort the listing counts in descending order to show the most common room types first
aib.groupby('room type')['id'].count().sort_values(ascending=False)

room type
Entire home/apt    50668
Private room       43940
Shared room         2119
Hotel room           112
Name: id, dtype: int64


# Count the number of occurrences of each 'Construction year' and reset the index
year_counts = aib['Construction year'].value_counts().reset_index()

# Rename the columns to 'Construction year' and 'Count'
year_counts.columns = ['Construction year', 'Count']

# Sort the year counts by 'Construction year'
year_counts = year_counts.sort_values(by='Construction year')

# Create a line plot using Plotly Express (imported as 'px')
fig = px.line(
    year_counts,
    x='Construction year',
    y='Count',
    title='Construction year vs. building constructed per year',  # Set the title of the plot
    markers=True,  # Show markers at data points
    hover_name='Construction year',  # Display 'Construction year' when hovering over data points
    hover_data={'Count': True},  # Show the count in the hover tooltip
    color_discrete_sequence=px.colors.qualitative.Set1,  # Define a color scheme
)

# Increase the size of the markers on the line plot
fig.update_traces(marker=dict(size=10))

# Update the layout of the plot
fig.update_layout(
    plot_bgcolor='white',  # Set the background color of the plot
    paper_bgcolor='white',  # Set the background color of the entire plot area
    title_font=dict(size=24, color='black'),  # Customize the title font size and color
    title_x=0.5,  # Center the title
)

# Customize the hover tooltip format
fig.update_traces(
    hovertemplate="Construction year: %{x}<br>Count: %{y:.0f} <extra></extra>"
)

# Customize the x-axis tick values and labels
fig.update_xaxes(
    tickmode='array',  # Use a fixed set of tick values
    tickvals=[year for year in range(min(year_counts['Construction year']), max(year_counts['Construction year']) + 1, 2)],  # Set the tick values
    ticktext=[year for year in range(min(year_counts['Construction year']), max(year_counts['Construction year']) + 1, 2)]  # Set the tick labels
)

# Display the plot
fig.show()


# Define custom colors for the bar chart
neighbor_palette = ['#FF5733', '#FFC300', '#DAF7A6']

# Calculate the average prices for each combination of 'neighbourhood group' and 'room type' and reset the index
avg_prices = aib.groupby(['neighbourhood group', 'room type'])['price'].mean().reset_index()

# Get unique room types
room_types = avg_prices['room type'].unique()

# Create a subplot with 2 rows and 2 columns, and set the figure size
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(9, 8))

# Iterate over each room type and create a bar chart for each
for i, room_type in enumerate(room_types):
    ax = axes[i // 2, i % 2]  # Select the current subplot
    subset = avg_prices[avg_prices['room type'] == room_type]  # Subset data for the current room type
    
    # Create a bar chart with neighborhood group on the x-axis and average price on the y-axis
    ax.bar(subset['neighbourhood group'], subset['price'], color=neighbor_palette)
    
    # Set the title, x-axis label, y-axis label, and add a horizontal grid
    ax.set_title(f'Room Type: {room_type}')
    ax.set_xlabel('Neighborhood')
    ax.set_ylabel('Avg Listings Prices')
    ax.grid(axis='y', linestyle='--', alpha=0.7)  # Add a horizontal grid with dashed lines
    ax.set_axisbelow(True)  # Ensure the grid is behind the bars

# Adjust the layout of the subplots for better spacing
plt.tight_layout()

# Set the main title for the entire figure
plt.suptitle('Avg Listings Prices by Neighborhood and Room Type', fontsize=16)

# Adjust the position of the main title to avoid overlap with subplots
plt.subplots_adjust(top=0.9)

# Display the plot
plt.show()


sorted_price = aib.sort_values('price', ascending=False)
top_10 = sorted_price.head(5)
top_10


# Create subplots with two rows and one column
fig = make_subplots(rows=2, cols=1, shared_xaxes=True, vertical_spacing=0.1)

# Data for the most expensive neighborhoods chart
top_neighbourhoods_expensive = aib.groupby('neighbourhood')['price'].median().nlargest(10).reset_index()
top_neighbourhoods_expensive = top_neighbourhoods_expensive.sort_values(by='price', ascending=True)

# Data for the least expensive neighborhoods chart
top_neighbourhoods_cheap = aib.groupby('neighbourhood')['price'].median().nsmallest(10).reset_index()
top_neighbourhoods_cheap = top_neighbourhoods_cheap.sort_values(by='price', ascending=False)

# Create the first subplot (most expensive neighborhoods)
trace1 = go.Bar(
    x=top_neighbourhoods_expensive['price'],
    y=top_neighbourhoods_expensive['neighbourhood'],
    orientation='h',
    marker=dict(color='skyblue'),
    name='Most Expensive'
)

# Create the second subplot (least expensive neighborhoods)
trace2 = go.Bar(
    x=top_neighbourhoods_cheap['price'],
    y=top_neighbourhoods_cheap['neighbourhood'],
    orientation='h',
    marker=dict(color='lightgreen'),
    name='Least Expensive'
)

# Add the traces to the subplots
fig.add_trace(trace1, row=1, col=1)
fig.add_trace(trace2, row=2, col=1)

# Update layout for both subplots
fig.update_layout(
    title_text="Top Ten Neighborhoods Comparison",
    title_x=0.5,
    showlegend=True,  # Show legends
    legend=dict(x=1, y=0.5),  # Adjust legend position
    plot_bgcolor='white',
    paper_bgcolor='white',
    height=800,
)

# Update labels for both subplots
fig.update_xaxes(title_text="Price [$]", row=2, col=1)
fig.update_yaxes(title_text=".                                                                      Neighbourhood\n\n\n", row=2, col=1)
 
# Show the combined subplot
fig.show()


# Create a scatter map using Plotly Express
fig = px.scatter_mapbox(aib,  # DataFrame containing data
           lat="lat",  # Latitude column
           lon="long",  # Longitude column
           opacity=0.3,  # Set marker opacity
           hover_name="neighbourhood group",  # Show 'neighbourhood group' when hovering
           hover_data=["neighbourhood group", "price"],  # Additional data to display on hover
           color="price",  # Color markers based on 'price' column
           color_continuous_scale='Viridis_r',  # Choose color scale
           title="Price comparing in the map",  # Set the title of the plot
           template="plotly",  # Choose the plot template
           zoom=10  # Set the initial zoom level
           )

# Increase the size of the plot and customize other layout options
fig.update_layout(
    mapbox_style="open-street-map",  # Choose mapbox style
    margin={"r": 10, "t": 50, "l": 10, "b": 10},  # Set plot margin
    font=dict(size=17, family="Franklin Gothic"),  # Customize font
    height=600  # Set the height of the plot
)

# Add interactivity - zoom, pan, and reset buttons
fig.update_mapboxes(
    zoom=10,  # Set the initial zoom level
)
fig.update_geos(
    projection_type="mercator",  # Use mercator projection for better interactivity
    showcoastlines=True,  # Show coastlines on the map
)

# Further layout adjustments
fig.update_layout(
    mapbox_style="open-street-map",  # Choose mapbox style
    margin={"r": 8, "t": 54, "l": 8, "b": 10},  # Set plot margin
    font=dict(size=17, family="Franklin Gothic"),  # Customize font
    height=600,  # Set the height of the plot
    title="Price comparing in the map",  # Set the title of the plot
    title_x=0.5,  # Set title's x position to the center
    title_y=0.95  # Set title's y position to the top
)

# Display the plot
fig.show()


# Clean and preprocess the 'house_rules' column
aib1['house_rules'] = aib1['house_rules'].fillna('')  # Replace NaN values with empty strings
house_rules_text = " ".join(aib1['house_rules'].astype(str))

# Create a WordCloud object with a larger size
wordcloud = WordCloud(width=1000, height=600, background_color='white').generate(house_rules_text)

# Create a centered figure
plt.figure(figsize=(12, 7))

# Calculate center position
x_centered = (plt.gca().get_xlim()[1] - plt.gca().get_xlim()[0]) / 2.0
y_centered = (plt.gca().get_ylim()[1] - plt.gca().get_ylim()[0]) / 2.0

# Display the Word Cloud in the center
plt.imshow(wordcloud, interpolation='bilinear', extent=[x_centered - 500, x_centered + 500, y_centered - 300, y_centered + 300])
plt.axis('off')
plt.title('House Rules')
plt.show()


review_rate_counts = aib['review rate number'].value_counts()

# Define the slice to explode (1 rating in this case)
explode_slice = "1"  # You may need to convert it to a string if it's not already

# Create a custom color palette for the slices
colors = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf']

# Create a list to specify the pull amount for each slice
explode_values = [0.1 if label == explode_slice else 0 for label in review_rate_counts.index]

# Create a pie chart using Plotly with a white border and exploded slice
fig = go.Figure(data=[go.Pie(
    labels=review_rate_counts.index,
    values=review_rate_counts,
    marker=dict(
        line=dict(color='white', width=2),  # Set white border
        colors=colors  # Apply the custom color palette
    ),
    hole=0.4,  # Adjust the size of the center hole if desired
    domain={"x": [0, 0.5]},  # Adjust the domain to explode the slice
)])

# Customize the layout
fig.update_layout(
    title_text="Distribution of Review Rates",
    title_x=0.17,  # Center the title horizontally
    legend=dict(x=0.5, y=0.3),  # Adjust the legend position (x and y coordinates)
)

# Show the pie chart
fig.show()


review_rate_per_neighbourhood_group = aib.groupby('neighbourhood group')['review rate number'].mean()


availability_per_neighbourhood_group = aib.groupby('neighbourhood group')['availability 365'].mean()


import plotly.graph_objects as go
from plotly.subplots import make_subplots
import plotly.express as px

# Assuming you have DataFrames named 'review_rate_per_neighbourhood_group' and 'availability_per_neighbourhood_group'
# Replace these with your actual data
# Both DataFrames should have the same index (neighborhood group names)

# Create subplots with 1 row and 2 columns
fig = make_subplots(rows=1, cols=2, subplot_titles=("Average Review Rate", "Average Availability"))

# Add the first bar plot for average review rate
trace1 = go.Bar(
    x=review_rate_per_neighbourhood_group.index,
    y=review_rate_per_neighbourhood_group.values,
    text=[str(round(i, 2)) for i in review_rate_per_neighbourhood_group.values],
    marker=dict(color=px.colors.sequential.algae),
    name="Review Rate"
)

# Add the second bar plot for average availability
trace2 = go.Bar(
    x=availability_per_neighbourhood_group.index,
    y=availability_per_neighbourhood_group.values,
    text=[str(round(i)) for i in availability_per_neighbourhood_group.values],
    marker=dict(color=px.colors.sequential.deep),
    name="Availability"
)

# Add the traces to the subplots
fig.add_trace(trace1, row=1, col=1)
fig.add_trace(trace2, row=1, col=2)

# Update the layout for the entire figure
fig.update_layout(
    title_text="Average Review Rate and Availability per Neighbourhood Group",
    font=dict(size=20, color='white', family='Avenir'),
    template='plotly_dark',
    showlegend=False  # Hide the legend as it's not needed in this case
)

# Show the merged plot
fig.show()


#I will categorize the price
aib["price"].median()

625.0


# Define a function 'cato_price' that categorizes prices
def cato_price(p):
    if p > 600:
        return "More than 600"
    else:
        return "less than 600"

# Apply the 'cato_price' function to each value in the 'price' column
aib["cat_price"] = aib["price"].apply(cato_price)


review_rate_per_neighbourhood_group = aib.groupby('neighbourhood group')['review rate number'].mean()


availability_per_neighbourhood_group = aib.groupby('neighbourhood group')['availability 365'].mean()


# Define the columns to be used for the parallel categories plot
labels = {"host_identity_verified": "Host Identity Verified", 
          "neighbourhood group": "Neighbourhood Group", 
          "room type": "Room Type", 
          "cat_price": "Price"}

# Create a parallel categories plot using Plotly Express
fig = px.parallel_categories(
    aib,
    dimensions=["host_identity_verified", "neighbourhood group", "room type", "cat_price"],  # Specify the columns to be used
    labels=labels  # Rename column labels for the plot
)

# Increase the figure size
fig.update_layout(
    width=1000,  # Set the width of the plot
    height=400  # Set the height of the plot
)

# Display the plot
fig.show()

	id	NAME	host id	host_identity_verified	host name	neighbourhood group	neighbourhood	lat	long	country	...	service fee	minimum nights	number of reviews	last review	reviews per month	review rate number	calculated host listings count	availability 365	house_rules	license
0	1001254	Clean & quiet apt home by the park	80014485718	unconfirmed	Madaline	Brooklyn	Kensington	40.64749	-73.97237	United States	...	$193	10.0	9.0	10/19/2021	0.21	4.0	6.0	286.0	Clean up and treat the home the way you'd like...	NaN
1	1002102	Skylit Midtown Castle	52335172823	verified	Jenna	Manhattan	Midtown	40.75362	-73.98377	United States	...	$28	30.0	45.0	5/21/2022	0.38	4.0	2.0	228.0	Pet friendly but please confirm with me if the...	NaN
2	1002403	THE VILLAGE OF HARLEM....NEW YORK !	78829239556	NaN	Elise	Manhattan	Harlem	40.80902	-73.94190	United States	...	$124	3.0	0.0	NaN	NaN	5.0	1.0	352.0	I encourage you to use my kitchen, cooking and...	NaN
3	1002755	NaN	85098326012	unconfirmed	Garry	Brooklyn	Clinton Hill	40.68514	-73.95976	United States	...	$74	30.0	270.0	7/5/2019	4.64	4.0	1.0	322.0	NaN	NaN
4	1003689	Entire Apt: Spacious Studio/Loft by central park	92037596077	verified	Lyndon	Manhattan	East Harlem	40.79851	-73.94399	United States	...	$41	10.0	9.0	11/19/2018	0.10	3.0	1.0	289.0	Please no smoking in the house, porch or on th...	NaN
5	1004098	Large Cozy 1 BR Apartment In Midtown East	45498551794	verified	Michelle	Manhattan	Murray Hill	40.74767	-73.97500	United States	...	$115	3.0	74.0	6/22/2019	0.59	3.0	1.0	374.0	No smoking, please, and no drugs.	NaN
6	1004650	BlissArtsSpace!	61300605564	NaN	Alberta	Brooklyn	Bedford-Stuyvesant	40.68688	-73.95596	United States	...	$14	45.0	49.0	10/5/2017	0.40	5.0	1.0	224.0	Please no shoes in the house so bring slippers...	NaN
7	1005202	BlissArtsSpace!	90821839709	unconfirmed	Emma	Brooklyn	Bedford-Stuyvesant	40.68688	-73.95596	United States	...	$212	45.0	49.0	10/5/2017	0.40	5.0	1.0	219.0	House Guidelines for our BnB We are delighted ...	NaN
8	1005754	Large Furnished Room Near B'way	79384379533	verified	Evelyn	Manhattan	Hell's Kitchen	40.76489	-73.98493	United States	...	$204	2.0	430.0	6/24/2019	3.47	3.0	1.0	180.0	- Please clean up after yourself when using th...	NaN
9	1006307	Cozy Clean Guest Room - Family Apt	75527839483	unconfirmed	Carl	Manhattan	Upper West Side	40.80178	-73.96723	United States	...	$58	2.0	118.0	7/21/2017	0.99	5.0	1.0	375.0	NO SMOKING OR PETS ANYWHERE ON THE PROPERTY 1....	NaN

	id	NAME	host_identity_verified	host name	neighbourhood group	neighbourhood	lat	long	instant_bookable	cancellation_policy	room type	Construction year	price	service fee	minimum nights	number of reviews	review rate number	calculated host listings count	availability 365
5207	3877162	Bushwick Room w/ Private Entrance & Bathroom!	unconfirmed	Julie	brookln	Bushwick	40.70322	-73.92913	True	strict	Private room	2020	1200	240	1	16	1	5	30
20343	12236775	Lovely apartment in Williamsburg	verified	Harry	brookln	Greenpoint	40.72253	-73.94350	True	flexible	Private room	2020	1200	240	7	6	2	1	62
17080	10434620	West 50th Street, Luxury Svcd Studio Apt	verified	Ken	manhattan	Hell's Kitchen	40.76294	-73.98574	True	flexible	Entire home/apt	2009	1200	240	30	1	4	87	329
75053	42453108	Cozy room in bright, spacious apartment	unconfirmed	Steven	bronx	Hunts Point	40.81731	-73.89052	False	moderate	Private room	2003	1200	240	21	0	2	4	341
50535	28911817	Stylish Petite Private Room in Brooklyn	verified	Shana	brookln	Bedford-Stuyvesant	40.67842	-73.91024	False	moderate	Private room	2020	1200	240	2	24	2	1	365

Group Number : 12¶

Name : Rutvik D Gadhiya , Harsh Sanjay Shah, Vrushabhkumar Shrimali¶

Percentage and Count of Airbnb Accomodation by room type¶

Avg listing price by neighbourhood¶

Bar chart of top ten neighborhoods price comparison.¶

Neighbourhood group in Map¶

Word cloud¶

Donut chart¶

AVG rate and Availability per Neighbourhood Group¶

Parallel Categorize Plot¶

Conclusion:¶